AU2022201358A1 - Method and apparatus for controlling an industrial gas plant complex - Google Patents
Method and apparatus for controlling an industrial gas plant complex Download PDFInfo
- Publication number
- AU2022201358A1 AU2022201358A1 AU2022201358A AU2022201358A AU2022201358A1 AU 2022201358 A1 AU2022201358 A1 AU 2022201358A1 AU 2022201358 A AU2022201358 A AU 2022201358A AU 2022201358 A AU2022201358 A AU 2022201358A AU 2022201358 A1 AU2022201358 A1 AU 2022201358A1
- Authority
- AU
- Australia
- Prior art keywords
- industrial gas
- predicted
- data
- dependent
- plant
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 110
- 230000036962 time dependent Effects 0.000 claims abstract description 85
- 238000005457 optimization Methods 0.000 claims abstract description 39
- 238000003860 storage Methods 0.000 claims description 124
- 238000010801 machine learning Methods 0.000 claims description 82
- 238000012549 training Methods 0.000 claims description 54
- 238000004146 energy storage Methods 0.000 claims description 37
- 230000007613 environmental effect Effects 0.000 claims description 22
- 239000007788 liquid Substances 0.000 claims description 10
- 241000196324 Embryophyta Species 0.000 description 257
- 239000007789 gas Substances 0.000 description 220
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 description 131
- 239000001257 hydrogen Substances 0.000 description 89
- 229910052739 hydrogen Inorganic materials 0.000 description 89
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 88
- 229910021529 ammonia Inorganic materials 0.000 description 66
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 52
- 238000004519 manufacturing process Methods 0.000 description 52
- 230000008569 process Effects 0.000 description 46
- 229910052757 nitrogen Inorganic materials 0.000 description 24
- 238000004422 calculation algorithm Methods 0.000 description 23
- 230000015572 biosynthetic process Effects 0.000 description 17
- 230000000670 limiting effect Effects 0.000 description 17
- 238000003786 synthesis reaction Methods 0.000 description 17
- 238000012423 maintenance Methods 0.000 description 15
- 230000001276 controlling effect Effects 0.000 description 13
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 13
- 230000006399 behavior Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 10
- 238000005259 measurement Methods 0.000 description 10
- 230000004044 response Effects 0.000 description 10
- 230000005611 electricity Effects 0.000 description 8
- 238000005868 electrolysis reaction Methods 0.000 description 8
- 238000010248 power generation Methods 0.000 description 8
- 238000012706 support-vector machine Methods 0.000 description 8
- -1 hydroxide ions Chemical class 0.000 description 7
- 238000000926 separation method Methods 0.000 description 7
- 238000006243 chemical reaction Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 239000001301 oxygen Substances 0.000 description 5
- 229910052760 oxygen Inorganic materials 0.000 description 5
- 230000000737 periodic effect Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000000746 purification Methods 0.000 description 5
- 239000007787 solid Substances 0.000 description 5
- 230000006835 compression Effects 0.000 description 4
- 238000007906 compression Methods 0.000 description 4
- 229910001873 dinitrogen Inorganic materials 0.000 description 4
- 239000003792 electrolyte Substances 0.000 description 4
- 239000002737 fuel gas Substances 0.000 description 4
- ZZUFCTLCJUWOSV-UHFFFAOYSA-N furosemide Chemical compound C1=C(Cl)C(S(=O)(=O)N)=CC(C(O)=O)=C1NCC1=CC=CO1 ZZUFCTLCJUWOSV-UHFFFAOYSA-N 0.000 description 4
- 238000007637 random forest analysis Methods 0.000 description 4
- 239000000243 solution Substances 0.000 description 4
- KWYUFKZDYYNOTN-UHFFFAOYSA-M Potassium hydroxide Chemical compound [OH-].[K+] KWYUFKZDYYNOTN-UHFFFAOYSA-M 0.000 description 3
- HEMHJVSKTPXQMS-UHFFFAOYSA-M Sodium hydroxide Chemical compound [OH-].[Na+] HEMHJVSKTPXQMS-UHFFFAOYSA-M 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013439 planning Methods 0.000 description 3
- 238000005086 pumping Methods 0.000 description 3
- 230000001932 seasonal effect Effects 0.000 description 3
- 230000006403 short-term memory Effects 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 235000014866 Dictamnus albus Nutrition 0.000 description 2
- 244000182625 Dictamnus albus Species 0.000 description 2
- 238000009620 Haber process Methods 0.000 description 2
- ATUOYWHBWRKTHZ-UHFFFAOYSA-N Propane Chemical compound CCC ATUOYWHBWRKTHZ-UHFFFAOYSA-N 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011049 filling Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 235000003642 hunger Nutrition 0.000 description 2
- 229910001872 inorganic gas Inorganic materials 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 229940075473 medical gases Drugs 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000036961 partial effect Effects 0.000 description 2
- 238000001556 precipitation Methods 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 239000013535 sea water Substances 0.000 description 2
- 238000001179 sorption measurement Methods 0.000 description 2
- 230000037351 starvation Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- MYMOFIZGZYHOMD-UHFFFAOYSA-N Dioxygen Chemical compound O=O MYMOFIZGZYHOMD-UHFFFAOYSA-N 0.000 description 1
- OTMSDBZUPAUEDD-UHFFFAOYSA-N Ethane Chemical compound CC OTMSDBZUPAUEDD-UHFFFAOYSA-N 0.000 description 1
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 1
- ZRXYMHTYEQQBLN-UHFFFAOYSA-N [Br].[Zn] Chemical compound [Br].[Zn] ZRXYMHTYEQQBLN-UHFFFAOYSA-N 0.000 description 1
- BNOODXBBXFZASF-UHFFFAOYSA-N [Na].[S] Chemical compound [Na].[S] BNOODXBBXFZASF-UHFFFAOYSA-N 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 239000012670 alkaline solution Substances 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 239000001273 butane Substances 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 239000003054 catalyst Substances 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 229910010293 ceramic material Inorganic materials 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000005115 demineralization Methods 0.000 description 1
- 238000010612 desalination reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 229910001882 dioxygen Inorganic materials 0.000 description 1
- 238000004821 distillation Methods 0.000 description 1
- 238000011143 downstream manufacturing Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 150000002431 hydrogen Chemical class 0.000 description 1
- 239000011261 inert gas Substances 0.000 description 1
- 229910001416 lithium ion Inorganic materials 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000012528 membrane Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- IJDNQMDRQITEOD-UHFFFAOYSA-N n-butane Chemical compound CCCC IJDNQMDRQITEOD-UHFFFAOYSA-N 0.000 description 1
- OFBQJSOFQDEBGM-UHFFFAOYSA-N n-pentane Natural products CCCCC OFBQJSOFQDEBGM-UHFFFAOYSA-N 0.000 description 1
- 239000004033 plastic Substances 0.000 description 1
- 229920003023 plastic Polymers 0.000 description 1
- 238000005381 potential energy Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 239000001294 propane Substances 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 239000003507 refrigerant Substances 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000000246 remedial effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
- 238000010977 unit operation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
- G05B19/4155—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by programme execution, i.e. part programme or machine function execution, e.g. selection of a programme
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2639—Energy management, use maximum of cheap power, keep peak load low
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32021—Energy management, balance and limit power to tools
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/41—Servomotor, servo controller till figures
- G05B2219/41108—Controlled parameter such as gas mass flow rate
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/30—Hydrogen technology
- Y02E60/36—Hydrogen production from non-carbon containing sources, e.g. by water electrolysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P20/00—Technologies relating to chemical industry
- Y02P20/10—Process efficiency
- Y02P20/133—Renewable energy sources, e.g. sunlight
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P80/00—Climate change mitigation technologies for sector-wide applications
- Y02P80/20—Climate change mitigation technologies for sector-wide applications using renewable energy
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Manufacturing & Machinery (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Feedback Control In General (AREA)
Abstract
There is provided a method of controlling an industrial gas plant complex comprising a plurality
of industrial gas plants powered by one or more renewable power sources, the method being
executed by at least one hardware processor, the method comprising receiving time
dependent predicted power data for a pre-determined future time period from the one or more
renewable power sources; receiving time-dependent predicted operational characteristic data
for each industrial gas plant; utilizing the predicted power data and predicted characteristic
data in an optimization model to generate a set of state variables for the plurality of industrial
gas plants; utilizing the generated state variables to generate a set of control set points for the
plurality of industrial gas plants; and sending the control set points to a control system to
control the industrial gas plant complex by adjusting one or more control set points of the
industrial gas plants.
1/6
160
- - - - - - - - - - - - -
12 :28
16a ----------
L2_ 121
18
LI ------- ---- i
I L -- - - - !L - - - -IL- - -
I I-------------------------------I
222
I II ---I
-------------
Fig I
I I *---Ijjjj--
A 10
L - - - - --
Description
1/6
160
12 :28 16a ---------- L2_ 121
18 LI ------- ---- i
222 III --I
Fig I
A I I *---Ijjjj--
10 L - - - - - -
[0001] The present invention relates to a method and system for controlling an industrial gas plant complex comprising a plurality of industrial gas plants powered by one or more renewable power sources.
[0002] An industrial gas plant complex may comprise one or more process plants which produce, or are involved in the production of, gases. In non-limiting examples, these gases may comprise: industrial gases, commercial gases, medical gases, inorganic gases, organic gases, fuel gases and green fuel gases either in gaseous, liquified or compressed form.
[0003] There is considerable interest in methods and systems for utilising renewable energy sources for powering industrial gas plants and industrial gas plant complexes. However, a significant drawback of the use of renewable energy sources such as wind, solar and tidal power is the natural variability and transient nature of such energy sources.
[0004] In general, a constant or substantially constant power supply is preferred for an industrial gas plant or industrial gas plant complex. Therefore, the variable and intermittent nature of wind, solar and/or tidal power is problematic and renders it difficult to ensure maximum utilisation of an industrial gas plant or industrial gas plant complex utilizing such power sources.
[0005] An exemplary industrial gas is Ammonia. Ammonia is produced using Hydrogen from water electrolysis and nitrogen separated from the air. These gases are then fed into the Haber-Bosch process, where Hydrogen and Nitrogen are reacted together at high temperatures and pressures to produce ammonia.
[0006] There is considerable interest in the production of Ammonia using renewable energy. This is known as green Ammonia. However, Ammonia synthesis can be particularly sensitive to the variation in input energy from renewable sources. Thus, solutions to these technical problems are required to enable industrial gases to be produced efficiently in such arrangements.
[0007] The following introduces a selection of concepts in a simplified form in order to provide a foundational understanding of some aspects of the present disclosure. The following is not an extensive overview of the disclosure, and is not intended to identify key or critical elements of the disclosure or to delineate the scope of the disclosure. The following merely summarizes some of the concepts of the disclosure as a prelude to the more detailed description provided thereafter.
[0008] According to a first aspect, there is provided a method of determining and utilizing predicted available power resources from one or more renewable power sources for one or more industrial gas plants comprising one or more storage resources, the method executed by at least one hardware processor, the method comprising: obtaining historical time dependent environmental data associated with the one or more renewable power sources; obtaining historical time-dependent operational characteristic data associated with the one or more renewable power sources; training a machine learning model based on the historical time-dependent environmental data and the historical time-dependent operational characteristic data; executing the trained machine learning model to predict available power resources for the one or more industrial gas plants for a pre-determined future time period; and controlling the one or more industrial gas plants in response to the predicted available power resources for the pre-determined future time period.
[0009] In embodiments, controlling the one or more industrial gas plants comprises maximizing the usage of the predicted available power resources forthe pre-determined future time period.
[0010] In embodiments, the storage resources comprise one or more industrial gas storage vessels and/or one or more energy storage resources.
[0011] In embodiments, the one or more energy storage resources comprises one or more of: battery energy storage systems; compressed air energy storage; liquid air energy storage; or pumped hydroelectric energy storage.
[0012] In embodiments, maximizing the usage of the predicted power resources further comprises controlling the utilization of the industrial gas storage vessels and/or one or more energy storage resources in response to the predicted available power resources.
[0013] In embodiments, controlling the utilization comprises utilizing an algorithm to select one or more storage resources from a group of storage resources for a given pattern of predicted power availability as a function of time.
[0014] In embodiments, selection of storage resources is based on physical characteristics of the storage resources.
[0015] In embodiments, the one or more renewable power sources comprise one or more of: solar power sources; wind power sources; tidal; hydro power; or geothermal power sources.
[0016] In embodiments, the environmental data is selected from one or more of: wind speed; cloud cover; precipitation; humidity; air temperature; atmospheric pressure; solar intensity; and tide times.
[0017] In embodiments, the operational characteristic data comprises power output from the one or more renewable power sources.
[0018] In embodiments, the step of training the machine learning model is carried out periodically at a pre-determined training time.
[0019] In embodiments, at the training time the machine learning model is trained based on historical time-dependent environmental data and the historical time-dependent operational characteristic data obtained within one or more pre-determined historical time windows.
[0020] In embodiments, the method further comprises comparing the value of the predicted power resources for a pre-determined future time period with the actual power resources at the end of the predicted period to generate a prediction error value.
[0021] In embodiments, the pre-determined training time is selected when the prediction error value exceeds a pre-determined threshold.
[0022] In embodiments, the pre-determined training time is selected based on a pre determined empirical interval unless the prediction error value exceeds the pre-determined threshold within the pre-determined empirical interval.
[0023] In embodiments, the one or more industrial gas plants comprise a Hydrogen production plant comprising at least one electrolyzer.
[0024] In embodiments, the one or more industrial gas plants comprise an Ammonia production plant complex including the Hydrogen production plant.
[0025] In embodiments, the machine learning model comprises one or more of: Gradient boosting algorithm; Long short-term memory (LSTM) algorithm; support vector machine (SVM) algorithm; or random decision forest algorithm.
[0026] According to a second aspect, there is provided a system for determining and utilizing predicted available power resources from one or more renewable power sources for one or more industrial gas plants comprising one or more storage resources, the system comprising: at least one hardware processor operable to perform: obtaining historical time-dependent environmental data associated with the one or more renewable power sources; obtaining historical time-dependent operational characteristic data associated with the one or more renewable power sources; training a machine learning model based on the historical time dependent environmental data and the historical time-dependent operational characteristic data; executing the trained machine learning model to predict available power resources for the one or more industrial gas plants for a pre-determined future time period; and controlling the one or more industrial gas plants in response to the predicted available power resources for the pre-determined future time period.
[0027] According to a third aspect, there is provided a computer readable storage medium storing a program of instructions executable by a machine to perform a method of determining and utilizing predicted available power resources from one or more renewable power sources for one or more industrial gas plants comprising one or more storage resources, the method comprising:obtaining historical time-dependent environmental data associated with the one or more renewable power sources; obtaining historical time-dependent operational characteristic data associated with the one or more renewable power sources; training a machine learning model based on the historical time-dependent environmental data and the historical time dependent operational characteristic data; executing the trained machine learning model to predict available power resources for the industrial gas plant for a pre-determined future time period; and controlling the one or more industrial gas plants in response to the predicted available power resources for the pre-determined future time period.
[0028] According to a fourth aspect, there is provided a method of monitoring operational characteristics of an industrial gas plant complex comprising a plurality of industrial gas plants, the method being executed by at least one hardware processor, the method comprising: assigning a machine learning model to each of the industrial gas plants forming the industrial gas plant complex; training the respective machine learning model for each industrial gas plant based on received historical time-dependent operational characteristic data for the respective industrial gas plant; executing the trained machine learning model for each industrial gas plant to predict operational characteristics for each respective industrial gas plant for a pre determined future time period; and comparing predicted operational characteristic data for each respective industrial gas plant for a pre-determined future time period with measured operational characteristic data for the corresponding time period to identify deviations in industrial gas plant performance.
[0029] In embodiments, the step of comparing is carried out at the end of the pre-determined future time period of the predicted operational characteristic data or at a timestamp therein.
[0030] In embodiments, the step of comparing comprises comparing predicted operational characteristic data predicted for a pre-determined time window with actual measured operational characteristic data for the same time window.
[0031] In embodiments, the received historical time-dependent operational characteristic data for the respective industrial gas plant comprises data obtained from a direct measurement of a process or parameter of the respective industrial gas plant.
[0032] In embodiments, the received historical time-dependent operational characteristic data for the respective industrial gas plant comprises data obtained from a physics-based model representative of operational characteristics of the respective industrial gas plant.
[0033] In embodiments, measured data relating to a process or parameter of the respective industrial gas plant is input into the respective physics-based model.
[0034] In embodiments, the predicted operational characteristics for each industrial gas plant are utilized to determine predicted future resources, future failure and/or predicted future maintenance.
[0035] In embodiments, one or more of the industrial gas plants comprises a hydrogen process plant having a plurality of electrolyzer modules.
[0036] In embodiments, each of the electrolyzer modules is assigned a machine learning model.
[0037] In embodiments, the predicted operational characteristics for each respective industrial gas plant are utilized in a further model to generate an operational performance metric of the industrial gas plant complex.
[0038] In embodiments, the operational performance metric comprises an efficiency value for the industrial gas plant complex.
[0039] In embodiments, the industrial gas plant complex comprises an Ammonia plant complex and the determined efficiency value enables a predicted determination of the Ammonia produced for a given level of energy input.
[0040] According to a fifth aspect, there is provided a system for monitoring operational characteristics of an industrial gas plant complex comprising a plurality of industrial gas plants, the system comprising at least one hardware processor operable to perform assigning a machine learning model to each of the industrial gas plants forming the industrial gas plant complex; training the respective machine learning model for each industrial gas plant based on received historical time-dependent operational characteristic data for the respective industrial gas plant; executing the trained machine learning model for each industrial gas plant to predict operational characteristics for each respective industrial gas plant for a pre determined future time period; and comparing predicted operational characteristic data for each respective industrial gas plant for a pre-determined future time period with measured operational characteristic data for the corresponding time period to identify deviations in industrial gas plant performance.
[0041] In embodiments, the step of comparing is carried out at the end of the pre-determined future time period of the predicted operational characteristic data or at a timestamp therein.
[0042] In embodiments, the step of comparing comprises comparing predicted operational characteristic data predicted for a pre-determined time window with actual measured operational characteristic data for the same time window.
[0043] In embodiments, the received historical time-dependent operational characteristic data for the respective industrial gas plant comprises data obtained from a direct measurement of a process or parameter of the respective industrial gas plant.
[0044] In embodiments, the received historical time-dependent operational characteristic data for the respective industrial gas plant comprises data obtained from a physics-based model representative of operational characteristics of the respective industrial gas plant.
[0045] In embodiments, the predicted operational characteristics for each industrial gas plant are utilized to determine predicted future resources, future failure and/or predicted future maintenance.
[0046] In embodiments, the predicted operational characteristics for each respective industrial gas plant are utilized in a further model to generate an operational performance metric of the industrial gas plant complex.
[0047] According to a sixth aspect, there is provided a computer readable storage medium storing a program of instructions executable by a machine to perform a method of monitoring operational characteristics of an industrial gas plant complex comprising a plurality of industrial gas plants, the method being executed by at least one hardware processor, the method comprising: assigning a machine learning model to each of the industrial gas plants forming the industrial gas plant complex; training the respective machine learning model for each industrial gas plant based on received historical time-dependent operational characteristic data for the respective industrial gas plant; executing the trained machine learning model for each industrial gas plant to predict operational characteristics for each respective industrial gas plant for a pre-determined future time period; and comparing predicted operational characteristic data for each respective industrial gas plant for a pre-determined future time period with measured operational characteristic data for the corresponding time period to identify deviations in industrial gas plant performance.
[0048] According to a seventh aspect, there is provided a method of controlling an industrial gas plant complex comprising a plurality of industrial gas plants powered by one or more renewable power sources, the method being executed by at least one hardware processor, the method comprising: receiving time-dependent predicted power data for a pre-determined future time period from the one or more renewable power sources; receiving time-dependent predicted operational characteristic data for each industrial gas plant; utilizing the predicted power data and predicted characteristic data in an optimization model to generate a set of state variables for the plurality of industrial gas plants; utilizing the generated state variables to generate a set of control set points for the plurality of industrial gas plants; and sending the control set points to a control system to control the industrial gas plant complex by adjusting one or more control set points of the industrial gas plants.
[0049] In embodiments, the optimization model defines the predicted power data and predicted characteristic data as a set of non-linear equations.
[0050] In embodiments, the state variables are generated by solving the set of non-linear equations.
[0051] In embodiments, the time-dependent predicted power data is generated from a trained machine learning model.
[0052] In embodiments, the time-dependent predicted power data is obtained by: obtaining historical time-dependent environmental data associated with the one or more renewable power sources; obtaining historical time-dependent operational characteristic data associated with the one or more renewable power sources; training a machine learning model based on the historical time-dependent environmental data and the historical time-dependent operational characteristic data; and executing the trained machine learning model to predict available power resources for the one or more industrial gas plants for a pre-determined future time period.
[0053] In embodiments, the time-dependent predicted operational characteristic data is generated from a trained machine learning model for each of the industrial gas plants.
[0054] In embodiments, the time-dependent predicted operational characteristic data for each industrial plant is obtained by: assigning a machine learning model to each of the industrial gas plants forming the industrial gas plant complex; training the respective machine learning model for each industrial gas plant based on received historical time-dependent operational characteristic data for the respective industrial gas plant; and executing the trained machine learning model for each industrial gas plant to predict operational characteristics for each respective industrial gas plant for a pre-determined future time period.
[0055] In embodiments, the industrial gas plant complex comprises storage resources comprising one or more industrial gas storage vessels and/or one or more energy storage resources.
[0056] In embodiments, the one or more energy storage resources comprises one or more of: battery energy storage systems; compressed air energy storage; liquid air energy storage; or pumped hydroelectric energy storage.
[0057] In embodiments, the predicted power data further comprises data representative of operational parameters of the storage resources.
[0058] In embodiments, the data representative of operational parameters of the storage resources comprises one or more of: resource storage availability; fill level; and utilization.
[0059] According to an eighth aspect, there is provided a system for controlling an industrial gas plant complex comprising a plurality of industrial gas plants powered by one or more renewable power sources, the system comprising: at least one hardware processor operable to perform: receiving time-dependent predicted power data for a pre-determined future time period from the one or more renewable power sources; receiving time-dependent predicted operational characteristic data for each industrial gas plant; utilizing the predicted power data and predicted characteristic data in an optimization model to generate a set of state variables for the plurality of industrial gas plants; utilizing the generated state variables to generate a set of control set points for the plurality of industrial gas plants; and sending the control set points to a control system to control the industrial gas plant complex by adjusting one or more control set points of the industrial gas plants.
[0060] In embodiments, the optimization model defines the predicted power data and predicted characteristic data as a set of non-linear equations.
[0061] In embodiments, the state variables are generated by solving the set of non-linear equations.
[0062] In embodiments, the time-dependent predicted power data is generated from a trained machine learning model.
[0063] In embodiments, the time-dependent predicted operational characteristic data is generated from a trained machine learning model for each of the industrial gas plants.
[0064] According to a ninth aspect, there is provided a computer readable storage medium storing a program of instructions executable by a machine to perform a of controlling an industrial gas plant complex comprising a plurality of industrial gas plants powered by one or more renewable power sources, the method being executed by at least one hardware processor, the method comprising: receiving time-dependent predicted power data for a pre determined future time period from the one or more renewable power sources; receiving time dependent predicted operational characteristic data for each industrial gas plant; utilizing the predicted power data and predicted characteristic data in an optimization model to generate a set of state variables for the plurality of industrial gas plants; utilizing the generated state variables to generate a set of control set points for the plurality of industrial gas plants; and sending the control set points to a control system to control the industrial gas plant complex by adjusting one or more control set points of the industrial gas plants.
[0065] In embodiments, the optimization model defines the predicted power data and predicted characteristic data as a set of non-linear equations.
[0066] In embodiments, the state variables are generated by solving the set of non-linear equations.
[0067] In embodiments, the time-dependent predicted power data is generated from a trained machine learning model and/or the time-dependent predicted operational characteristic data is generated from a trained machine learning model for each of the industrial gas plants.
[0068] Embodiments of the present invention will now be described by example only and with reference to the figures in which:
[0069] FIGURE 1 is a schematic diagram of an industrial gas plant complex and control system;
[0070] FIGURE 2 is a detailed schematic diagram of the control system of Figure 1;
[0071] FIGURE 3 is a graph showing measured and predicted wind power values using a model according to an embodiment of the present invention;
[0072] FIGURE 4 is a graph showing measured and predicted solar power values using a model according to an embodiment of the present invention;
[0073] FIGURE 5 is a flow chart of a method according to an embodiment;
[0074] FIGURE 6 is a flow chart of a method according to an embodiment;
[0075] FIGURE 7 is a graph showing the efficiency model for a process variable;
[0076] FIGURE 8 is a graph of optimal Ammonia plant rate as a function of time for a 48 hour predicted period; and
[0077] FIGURE 9 is a flow chart of a method according to an embodiment.
[0078] Embodiments of the present disclosure and their advantages are best understood by referring to the detailed description that follows. It should be appreciated that like reference numbers are used to identify like elements illustrated in one or more of the figures, wherein showings therein are for purposes of illustrating embodiments of the present disclosure and not for purposes of limiting the same.
[0079] Various examples and embodiments of the present disclosure will now be described. The following description provides specific details for a thorough understanding and enabling description of these examples. One of ordinary skill in the relevant art will understand, however, that one or more embodiments described herein may be practiced without many of these details. Likewise, one skilled in the relevant art will also understand that one or more embodiments of the present disclosure can include other features and/or functions not described in detail herein. Additionally, some well-known structures or functions may not be shown or described in detail below, so as to avoid unnecessarily obscuring the relevant description.
[0080] Figure 1 shows a schematic diagram of an industrial gas plant complex 10 and a control system 100.
[0081] The industrial gas plant complex 10 comprises a Hydrogen production plant 12, a Hydrogen storage unit 14, an Air Separation Unit (ASU) 16, an Ammonia synthesis plant 18 and an ammonia storage unit 20. The ammonia storage unit 20 is connected to an external supply chain 22 for onward distribution of Ammonia.
[0082] Electricity for powering the industrial gas plant complex 10 is generated at least in part by renewable energy sources such as wind 24 and/or the solar 26 although other sources such as a diesel-, petrol- or hydrogen-powered generator (not shown) or a national power grid (not shown) may optionally be utilised.
[0083] To address the intermittency of power supply from renewable sources, a storage resource 28 is provided. The storage resource 28 may comprise one or more resource storage devices or energy storage devices. For example, the one or more resource storage devices may include the Hydrogen storage unit 14. Hydrogen production through electrolysis requires a significant amount of power and the use of stored Hydrogen as a Hydrogen source for Ammonia production may significantly reduce the power consumption of the plant 10 during periods of low renewable power supply. Additionally, liquid Nitrogen storage 16a may also be provided as part of the storage resource 28 as shown in Figure 1.
[0084] Additionally or alternatively, in non-exhaustive arrangements, the energy storage devices may comprise one or more of: a Battery Energy Storage System (BESS) 28a, a Compressed/Liquid Air Energy Systems (CAES or LAES) 28b or a Pumped Hydro Storage System (PHSS) 28c.
[0085] A BESS 28a utilises electrochemical techniques and may comprise one or more of: Lithium Ion batteries, Lead acid batteries, Zinc Bromine, Sodium Sulphur or Redox Flow batteries. Electro-chemical arrangements such as batteries have advantages in terms of fast charging rates and fast (virtually instantaneous) ramp rates to supply power to cope with a sudden drop in energy supply. However, they tend to be of more limited power capacity than other systems. Therefore, they may be better suited for use in situations where, for example, a power shortfall from renewable sources is expected to be temporary or short in duration.
[0086] A CAES 28b compresses air and stores the air under a high pressure of around 70 bar. It is usually stored in an underground cavern. When power is required, the compressed air is heated and expanded in an expansion turbine in order to drive a generator.
[0087] A LAES 28b comprises an air liquefier to draw air from the environment and compress and cool the air to achieve liquefaction. The liquified air is then stored in an insulated tank until power is required. To convert the liquified air into useable energy, the liquid air is pumped to high pressure and heated through heat exchangers. The resulting high-pressure gas is used to drive a turbine to generate electricity.
[0088] CAES and LAES are capable of storing significantly more energy than most BESS 28a systems. However, CAES and LAES have slower ramp rates than electro-chemical storage devices and require longer to store larger quantities of energy. For example, it may take of the order of 5-10 minutes for a compression stage to operate under full load, and 10 - 20 minutes to generate full power on demand. Such storage devices are therefore more appropriate for longer-term storage and for supplying power during long periods of renewable energy shortfall.
[0089] A PHSS 28c stores energy in the form of gravitational potential energy by pumping water from a lower elevation reservoir to a higher elevation reservoir. When power is required, the water is released to drive turbines. Some PHSS arrangements utilised a reversible pump turbine unit.
[0090] Given the large storage capacity of PHSS configurations, they are often suited to longer-term storage. In addition, particularly for reversible pump turbines, timescales of the order of 5-10 minutes from shutdown to full load generation, 5 to 30 minutes from shut down to pumping, and 10 to 40 minutes for pumping to load generation or vice vera are common. Thus, such storage would appear more appropriate for longer term power deficits.
[0091] Whilst all these elements are shown in Figure 1, this is for illustrative purposes only. The energy storage resource 20 need not comprise each and every described element and may comprise only one or more of the described elements. In addition, the energy resource 28 may comprise additional elements.
[0092] The components of the industrial gas plant complex 10 will now be described in detail.
[0093] HYDROGEN PRODUCTION PLANT 12
[0094] The Hydrogen production plant 12 is operable to electrolyse water to form Hydrogen and Oxygen. Any suitable source of water may be used. However, in embodiments in which sea water is used to produce the water for the electrolysis, the apparatus would further comprise at least one desalination and demineralisation plant to for processing the sea water.
[0095] The Hydrogen production plant 12 comprises a plurality of electrolysis units 12a, 12b ... 12n or electrolysis cells. Each unit or cell may be referred to as an "electrolyser" 12a, 12b ... 12n.
[0096] The electrolysers may enable the Hydrogen production plant 12 to have a total capacity of at least 1 GW. However, the ultimate capacity of the Hydrogen production plant 12 is limited only by practical considerations such as power supply.
[0097] Any suitable type of electrolyser may be used. In embodiments, the plurality of electrolysers usually consists of a multiplicity of individual cells combined into "modules" that also include process equipment such as pumps, coolers, and/or separators. Hundreds of cells may be used and may be grouped in separate buildings. Each module typically has a maximum capacity greater than 10 MW, although this is not intended to be limiting.
[0098] Any suitable type of electrolyser may be used with the present invention. Generally, three conventional types of electrolyser are utilized - alkaline electrolysers; PEM electrolysers; and solid oxide electrolysers. Any of these types may be used with the present invention.
[0099] Alkaline electrolysers transport hydroxide ions (OH-) through the electrolyte from the cathode to the anode with hydrogen being generated on the cathode side. Commonly, a liquid alkaline solution of sodium hydroxide or potassium hydroxide is used as the electrolyte.
[0100] A PEM electrolyser utilizes a solid plastics material as an electrolyte, and water reacts at an anode to form oxygen and positively charged hydrogen ions. The electrons flow through an external circuit and the hydrogen ions selectively move across the PEM to the cathode. At the cathode, hydrogen ions combine with electrons from the external circuit to form hydrogen gas.
[0101] Solid oxide electrolysers use a solid ceramic material as the electrolyte that selectively conducts negatively charged oxygen ions (02-) at elevated temperatures. Water at the cathode combines with electrons from the external circuit to form hydrogen gas and negatively charged oxygen ions. The oxygen ions pass through the solid ceramic membrane and react at the anode to form oxygen gas and generate electrons for the external circuit.
[0102] The electrolysers may be arranged in any suitable group. For example, they may be arranged in parallel.
[0103] Hydrogen is produced at about atmospheric pressure by the Hydrogen production plant 12. A stream of hydrogen so generated is removed from the electrolysers at a slightly elevated pressure and may be transferred via a pipe to the Ammonia synthesis plant 18.
[0104] Alternatively, any Hydrogen surplus to requirements may be stored in the Hydrogen storage unit 14. The storage unit 14 comprises of a plurality of short-term and longer-term storage options with different sizes, filling/discharge rates, and roundtrip efficiencies. Typical storage system could include pressure vessels and/or pipe segments connected to a common inlet/outlet header. The pressure vessels may be spheres, for example, to about 25 m in diameter, or "bullets" which are horizontal vessels with large L/D ratios (typically up to about 12:1) with diameters up to about 12 m. In certain geographies, underground caverns are included as storage systems to flatten out the seasonal variations associated with the renewable power.
[0105] Preferably, the Hydrogen gas is compressed by a compressor and stored in the Hydrogen storage unit 14 under pressure to reduce volume requirements. It may be used commercially at this point (e.g. sold for automotive purposes) or may be used as a reservoir for Ammonia synthesis plant 18 via pipe 30.
[0106] Optionally, a purification system may be implemented to purify or dry the Hydrogen before onward use. For example, the Hydrogen may be dried in an adsorption unit, such as a temperature swing adsorption (TSA) unit for the downstream process(es).
[0107] AIR SEPARATION UNIT 16
[0108] In non-limiting embodiments, the Nitrogen gas required for Ammonia production is produced by cryogenic distillation of air in the air separation unit (ASU) 16. Typically an ASU 16 operates at a pressure of around 10 bar. The pressure is then reduced to provide a stream of Nitrogen gas in one or more pipes arranged to transport Nitrogen to the Ammonia Synthesis plant 16. However, other Nitrogen sources may be used if required, for example, Nitrogen storage 16a.
[0109] A Nitrogen gas storage unit 16a may also be provided, which can be used as a resource storage as described below. The storage unit 16a may, in common with the Hydrogen storage unit 14, comprise a plurality of short-term and longer-term storage options having different sizes, filling/discharge rates, and roundtrip efficiencies.
[0110] A typical storage system for Nitrogen may comprise a plurality of pressure vessels and/or pipe segments connected to a common inlet/outlet header. The pressure vessels may be spheres, for example, to about 25 m in diameter, or "bullets" which are horizontal vessels with large L/D ratios (typically up to about 12:1) with diameters up to about 12 m. In certain geographies, underground caverns may be utilised to flatten out the seasonal variations associated with the renewable power.
[0111] Preferably, the Nitrogen gas is compressed by a compressor and stored in the Nitrogen storage unit 16a under pressure to reduce volume requirements. It may be used as a reservoir for Ammonia synthesis plant 18 which may be fed by a connecting pipe.
[0112] AMMONIA SYNTHESIS PLANT 18
[0113] The Ammonia Synthesis plant 18 operates on the Haber-Bosch process and comprises an Ammonia Loop. An Ammonia Loop is a single unit equilibrium reactive system which processes the synthesis gas of Nitrogen and Hydrogen to produce Ammonia.
[0114] Nitrogen is provided by one or more pipes from the ASU 16 which, in embodiments, may run continuously to provide Nitrogen. Hydrogen is provided from one or more pipe from Hydrogen production plant 12 (if it is running based on the availability of the renewable power at given instance) otherwise Hydrogen is fed from the Hydrogen storage 14.
[0115] Stoichiometric composition of synthesis gas is processed by a syn-gas compressor system and the resulting Ammonia product is refrigerated by another set of compressors and sent to storage. The performance of Ammonia loop is governed by the equilibrium conversion of the exothermic reaction. The parameters for this will be discussed below.
[0116] ELECTRICITY GENERATION AND MANAGEMENT SYSTEM
[0117] Electricity for the plant 10 as a whole may be generated from any suitable energy source, including renewable or non-renewable energy sources. As shown in Figure 1, the electricity is generated from at least one renewable energy source of either wind energy 24 (via a suitable wind farm comprising a plurality of wind turbines) and/or solar energy 26 (via a solar farm comprising a plurality of solar cells). In addition, other renewable energy sources may be used such as hydro-electric (not shown) and/or tidal power (not shown).
[0118] In addition, electricity or resources for the plant 10 as a whole or for sub-plants of the plant 10 may be drawn from the energy storage resource 28. As described with respect to Figure 1, the energy storage resource 28 may comprise one or more storage resources. For example, the one or more storage resources may include the Hydrogen storage unit 14 and Nitrogen storage 16a.
[0119] Additionally or alternatively, in non-exhaustive arrangements, the energy storage devices may comprise one or more of: a Battery Energy Storage System (BESS) 28a, a Compressed/Liquid Air Energy Systems (CAES or LAES) 28b or a Pumped Hydro Storage System (PHSS) 28c.
[0120] These elements are used optimally to store additional resources and/or energy when electricity provision from renewable sources is high or predicted to be high and then utilise those resources and/or energy when renewable electricity resources are predicted to be low.
[0121] The prediction and control of these facilities will be described below. Selection of these facilities under optimal conditions is important such that the correct energy source is selected for a particular predicted power shortfall period, for example.
[0122] CONTROL SYSTEM 100
[0123] The control system 100 of Figure 1 is shown in detail in the schematic of Figure 2.
[0124] The control system 100 comprises three main categories: plant complex control systems 110, renewable energy control systems 120 and an optimization system 150. These are non-limiting terms and do not necessarily imply any interconnection or grouping between the component parts of the systems 110, 120, 150 and are illustrated in a common grouping for clarity purposes only.
[0125] The plant complex control systems 110 comprise a Hydrogen production plant control system 112, a Hydrogen storage control system 114, an ASU control system 116 and an Ammonia synthesis plant control system 118.
[0126] By way of example, the Hydrogen production plant control system 112 may be configured to monitor the amount and rate of generation of Hydrogen gas from the electrolysis by measurement. Such a measurement may be derived from sensor measurements such as direct flow measurements, or alternatively inferred through indirect measurements such as the electrolyser current or power demand.
[0127] By way of further example, for the Hydrogen storage control system 114, the pressure and flow of compressed hydrogen from electrolyser and compression system to the storage system may be monitored, as well as the pressure and flow of compressed hydrogen gas to the Ammonia synthesis plant 18.
[0128] In each case the control systems 110 are operable to control the parameters of the respective industrial gas plant and are able to output use and process data from each industrial gas plant. This will be described in detail below.
[0129] The renewable energy control systems 120 in the described embodiments comprise the wind control system 124 and solar control system 126. These control systems control and monitor process parameters of the renewable energy source such as energy generation, storage and load. They are also configured to send usage, power and process data to external systems as required. If hydro-electric or tidal renewable power sources are used, similar control systems will apply.
[0130] The optimization system 150 comprises a computer system including three modules: a power prediction module 152, a plant operation module 154 and a real-time optimization module 156.
[0131] The power prediction module (PPM) 152 receives usage and power generation data from the renewable energy control systems 120 and also from a weather and forecast database 160 which comprises information relating to past (known and historical) environmental and weather data and future (predicted and forecast) environmental and weather data. The power prediction module 152 comprises a machine learning algorithm implemented on a computing system as will be described below and is used to generate a model relating to future power generation.
[0132] The plant operation module (POM) 154 is operable to receive plant operation data from the plant complex control systems 110 and generate a model of the plant operation. The plant operation module 152 comprises a machine learning algorithm implemented on a computing system as will be described below.
[0133] The real-time optimization module (RTOM) 156 is arranged to receive inputs from the power prediction module 152 and plant operation module 154 and derive a plant operation policy strategy including setpoint operation parameters. These are then fed to the plant complex control systems 110 to control the relevant processes controlled thereby.
[0134] The detail and operation of each component will now be described.
[0135] POWER PREDICTION MODULE (PPM) 152
[0136] The power prediction module 152 comprises a machine learning algorithm implemented on a computing system and operable to generate a model to predict future power generation. In embodiments, an aspect of the power prediction module 152 is to be able to predict future power generation from a variable and/or intermittent source such as a renewable power source so that one or more industrial gas plants (which in general require a constant power load) can be controlled without risk of power starvation of the plants.
[0137] In embodiments, a further aspect of the power prediction module 152 is to use the predicted power generation data to control the plant complex 10 or aspects thereof. This will be discussed in more detail below.
[0138] The model used to predict future power is based on a machine learning framework. Any suitable machine learning algorithm may be used. For example, the model may utilise techniques such as Gradient boosting (utilising, for example, XGboost), Long short-term memory (LSTM), support vector machine (SVM) or random decision forests may be used in such a model.
[0139] Gradient boosting is a machine learning technique utilized in regression and classification problems. A strong prediction model is formed which comprises an ensemble of weak prediction models such as decision trees. A stage-wise process may be used to generate the model through steepest descent minimisation (amongst others).
[0140] LSTM is an artificial recurrent neural network architecture which has feedback connections as well as feedforward connections. A common LSTM unit is composed of a cell, an input gate, an output gate and a forget gate. The cell is operable to remember values over an arbitrary time interval the flow of information into and out of the cell is regulated by the gates.
[0141] A support vector machine utilises a set of training examples, each comprised in one of two categories, and generates a model that assigns new examples to a particular category. Thus, a SVM comprises a non-probabilistic binary linear classifier.
[0142] Random decision forests comprise ensemble machine learning methods which operate by constructing a multitude of decision trees during a training process and outputting the class that is the mode of the classes (classification) or mean/average prediction (regression) of the individual trees.
[0143] Irrespective of the machine learning algorithm used, the model utilises a two step operation process where a training stage is required prior to a predictive stage. Both stages are implemented as computer programs on one or more computer systems.
[0144] Specialist hardware may also be used. For example, the training stage may involve use of Central Processing unit (CPU) and Graphical Processing Unit (GPU) components of a computer system. In addition, other specialist hardware may be used such as Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs) or other stream processor technologies.
[0145] TRAINING STAGE
[0146] The model is trained periodically (for example, on a daily basis) or on demand (if, for example, the accuracy of the model demands a training process) to create a relationship between predicted variables of the renewable energy power plant to determine predicted energy availability for a pre-determined future period.
[0147] The PPM 152 aims to determine the predicted variables of:
[0148] Wind power WPi
[0149] Solar Power SPi
[0150] where the index i represents time from period n to n+k in intervals of fixed duration. In non-limiting embodiments, the intervals may comprise 15 minutes or 1 hour.
[0151] The predictor variables comprise time-dependent operational characteristic data of the are:
[0152] Wind power WPi
[0153] Solar Power SPi
[0154] Power load Lifrom the period n-m to n-1.
[0155] The predictor variables also include measured environmental and meteorological signals which may comprise but are not limited to time-dependent environmental data comprising:
[0156] Airtemperature Ti,
[0157] Atmospheric pressure Pi
[0158] Wind speed WSi,
[0159] Cloud cover CCI,
[0160] Precipitation Pi
[0161] Humidity Hi
[0162] where index i represents time from period n-m to n+k.
[0163] In the training stage, various machine learning algorithms are used to create a mathematical relationship between the predicted and predictor variables. These relationships are stored in the computer as a series of equations that can be accessed and used to make future predictions.
[0164] These models are generated during a training process which is carried out periodically at a pre-determined training time. At each training time the machine learning model is trained based on the historical time-dependent environmental data and the historical time-dependent operational characteristic data obtained within one or more pre-determined historical time windows. In other words, a moving historical window of time-dependent data (e.g. the previous 2 days, the previous 2-weeks etc.) is used to train the machine learning model.
[0165] As noted above, meteorological measurements come from the weather and forecast database 160 which may comprise a weather data service or other internet-connected resource. Load, solar power and wind power are measured by the operator or fed via the renewable energy control systems 120 as part of an automated data collection system.
[0166] PREDICTION STAGE
[0167] In the prediction stage, the equations generated and stored in the training phase are used to enable predictions regarding future behaviour to be made.
[0168] The predicted variable comprises a forecast of wind power WPi and solar power SPi for from c+1 to c+p, where c represents current time and p represents a prediction horizon which could be any suitable timescale; for example, non-limiting examples may be 24 hours, 48 hours or more.
[0169] The predictor variables are:
[0170] Wind power WPi
[0171] Solar Power SPi
[0172] Power load Li
[0173] from c-r to c, measured meteorological signals (as per the training phase), and forecast meteorological signals from c+1 to c+p.
[0174] As for the training phase, environmental and meteorological measurements come from, in embodiments, the weather and forecast database 160 which may comprise a weather data service or other internet-connected resource. Load, solar power and wind power are measured by the operator or fed via the renewable energy control systems 120 automatically.
[0175] Figures 3 and 4 show prediction of wind power and solar power where the predicted variables are generated from the model prediction stage above.
[0176] In embodiments, an assessment of the accuracy of the machine learning model is made by comparing a value of the predicted power resources for a pre-determined future time period with the actual power resources which were available to the industrial gas plant at the end of the predicted future time period. This enables determination of a prediction error value which provides a metric for the accuracy of the model.
[0177] If the model is insufficiently accurate, it may need to be trained at a further training time. The pre-determined training time may be selected based on the prediction error value which may, in embodiments, be when the prediction error value exceeds a pre-determined threshold.
[0178] In embodiments, the training time may be selected empirically on a periodic basis; for example, every 24 hours or every 48 hours as appropriate. In embodiments, this periodic basis may be the default training time strategy.
[0179] However, in embodiments, this may be interrupted when the prediction error value exceeds the pre-determined threshold within the pre-determined empirical interval, in which case the training time is scheduled based on the prediction error value.
[0180] CONTROL BASED ON PREDICTED DATA
[0181] The PPM 152 may utilise the predicted data to control the one or more industrial gas plants in response to the predicted available power resources for the pre-determined future time period. For example, in addition to the RTM 156, the PPM 152 may control operational aspects of the of the one or more industrial gas plants.
[0182] In embodiments, the forecast power data may additionally or alternatively control the use of the storage resource 28. As described above, the storage resource 28 may comprise resource storage such as stored Hydrogen and/or Nitrogen, and energy storage through BESS 28a, CAES/LAES 28b and PHSS 28c amongst others.
[0183] The PPM 152 may therefore comprise a control and optimization algorithm which utilizes the predicted power resources to optimize usage of the available storage resources 28 to run the plant complex 10 optimally and to plan for future power availability and power usages.
[0184] The PPM 152 system uses the predicted powers WPi and SPi as inputs in a real-time optimization problem and applies an optimization algorithm to propose optimal rates at which to run the industrial gas complex 10 to maximize the utilisation of the available power and the stored resources in the resource storage 28.
[0185] For example, expected daily and seasonal variability in predicted power generation may be addressed by the PPM 152 by determining an optimal use of short-term (e.g. BESS 28a) and longer-term (e.g. CAES/LAES 28b and PHSS 28c) storage systems in the storage resource 28.
[0186] In embodiments, the PPM 152 may determine optimal power up and shut down times for storage resources 28 to maximize available power utilization. Examples of this will be described below.
[0187] In a non-limiting example, the PPM 152 may determine that sufficient power is available over the next 24 hours to run the electrolyzers 12a.. .n of the Hydrogen production plant 12 under greater load to generate more Hydrogen than required to produce an optimal Ammonia production rate over the predetermined time period. The additional Hydrogen may then be stored in the Hydrogen storage 14 for use during lower power availability periods. The same may apply to the ASU 16 and Nitrogen storage 16a.
[0188] The PPM 152 may receive operational characteristic data for the Hydrogen storage 14 and Nitrogen storage 16a. This may include fill levels and other operational data (e.g. fill pressures, fill volume, density etc.) This operational data may be used by an algorithm forming part of the PPM 152 to determine optimal storage requirements to address predicted future power availability distribution as a function of time.
[0189] In embodiments, the PPM 152 may also determine that sufficient power is available over a predicted time window to store additional power in the energy storage 28a, 28b, 28c. The PPM 152 may utilize an optimization algorithm to select the appropriate energy storage 28a, 28b, 28c depending upon the power availability vs time predictions.
[0190] In a non-limiting example, the PPM 152 may determine that power availability in excess of plant complex 10 demand is available for a relatively short period (e.g. 1-2 hours). It may then be determined that BESS 28a represents the most appropriate energy storage solution for that time period given the short ramp rate, fast charging time and lower capacity of BESS 28a solutions.
[0191] In an alternative non-limiting example, the PPM 152 may determine that significant power availability in excess of plant complex 10 demand is available for a longer period (e.g. -10 hours). In this situation, it may then be determined that CAES/LAES 28b and PHSS 28c may be better suited to storage of the available power given the slower ramp rates and higher storage capacity of such energy storage solutions.
[0192] The PPM 152 system solves the optimization problem for the next p time periods applies the available power predictions in a real time optimization model to maximize the utilization of power. The model may involve the generation of a power utilization metric and the optimization seeks to optimize the value of the power generation metric.
[0193] The PPM 152 may also comprise a tracking system to calculate the predicted power utilization metric as a function of complementarity of renewable power resources and adjust the generations levels/utilization to maximize long term utilization of renewable resources.
[0194] The PPM 152 system is implemented on a computer and receives various inputs from other computer systems. An example of the PPM 152 system may utilise Mixed Integer Non Linear Programs (MINLP) because some of the decisions require some equipment to be run in one of multiple possible modes leading to integer variables. Figure 5 shows a method according to an embodiment. Note the following steps need not be carried out in the order described below and some steps may be carried out concurrently with other steps.
[0195] In embodiments, a method of predicting available power resources from one or more renewable power sources for one or more industrial gas plants is provided. The method executed by at least one hardware processor.
[0196] At step 200, historical time-dependent environmental data associated with the one or more renewable power sources 24, 26 is obtained. By historical is meant past environmental data. This may be gathered in any suitable time window, and may include data within a window which extends up to but not including the present time.
[0197] At step 210, historical time-dependent operational characteristic data associated with the one or more renewable power sources. By historical is meant past operational characteristic data such as power output. This may be gathered in any suitable time window, and may include data within a window which extends up to but not including the present time.
[0198] At step 220, a machine learning model is trained based on the historical time dependent environmental data and the historical time-dependent operational characteristic data captured in steps 200 and 210. The model may be trained any suitable number of times and at pre-determined intervals or on demand.
[0199] At step 230, the trained machine learning model is executed to predict available power resources for the one or more industrial gas plants for a pre-determined future time period.
[0200] At step 240, the predicted data may optionally be used to control the one or more industrial gas plants in response to the predicted available power resources for the pre determined future time period. For example, one or more operational setpoints of the one or more industrial gas plants may be set in dependence upon the predicted available power resources.
[0201] In addition, as described above, an optimization algorithm may be utilized based on the predicted available power resources for a pre-determined future period to determine how best to manage storage resource 28 which includes resource storage such as Hydrogen storage 14 and Nitrogen storage 16 and energy storage resources 28a, 28b, 28c. The optimization algorithm may select the optimal scheduling and/or select the optimal resources for a given pattern of predicted power availability as a function of time.
[0202] The selection and scheduling may be based on operational characteristics of the storage resources; for example, the fill levels, pressures and other characteristics of the Hydrogen and Nitrogen storage 14, 16a, or the ramp up/ramp down, time dependency, maximum generated power/maximum stored energy operational profiles of the energy storage resources 28a, 28b, 28c.
[0203] At step 250, a determination is made as to whether a further training process is required. This may be based on an empirical metric such as a pre-determined time period. Alternatively, it may be based on an assessment of the accuracy of the machine learning model by comparing a value of the predicted power resources for a pre-determined future time period with the actual power resources which were available to the industrial gas plant at the end of the predicted future time period. This enables determination of a prediction error value which provides a metric for the accuracy of the model.
[0204] If it is determined that the model needs retraining, a training time may be scheduled and the method may move back to training in step 220. Note that this may occur following or during either of steps 230 or 240.
[0205] PLANT OPERATION MODULE (POM) 154
[0206] Optimization of the plant process control is critical to achieving efficiency. Given that renewable power sources will nearly always result in variations in the available power, the industrial gasplant complex 10 may frequently be operating in a dynamic mode. This requires real-time performance models to devise a robust operational strategy. The POM 154 comprises a machine learning and physics-based model to model plant operation. The physics-based models may be utilised to generate predictor variables indicative of operational characteristics of the respective industrial gas plant. These may be used, in embodiments, together with other operational plant data (e.g. power input, power output, gas output) as time dependent data inputs to a respective machine learning model.
[0207] As noted above, the industrial gasplant complex 10 comprises the Hydrogen production plant 12, the Hydrogen storage unit 14, the Air Separation Unit (ASU) 16, the Ammonia synthesis plant 18 and the ammonia storage unit 20, some of which are controlled by respective control systems: Hydrogen production plant control system 112, Hydrogen storage control system 114, ASU control system 116 and Ammonia synthesis plant control system 118.
[0208] At every time step, in embodiments, the power availability forecast from PPM 152 is used to define the operational setpoints of the different industrial gas plants 112, 114, 116, 118.
[0209] These decisions are operable in embodiments to achieve a high process efficiency. This requires accurate quantitative understanding of the different process units in terms of their real-time performance, system availability information together with resource availability and impending maintenance issues.
[0210] The POM 154 is configured to capture the time-varying attributes for each of the subsystems (i.e. the respective industrial gas plants) and predict the production efficiency of the overall process in terms of Ammonia produced for a given level of energy consumed.
[0211] A high-fidelity model for such a prediction is based on real-time machine learning framework, which uses time-dependent historical data provided by aa Distributed Control System (DCS) in the form of time series for various process tags. Any suitable machine learning algorithm may be used to build ensemble models for individual subsystems. For example, the model may utilise techniques such as Gradient boosting (utilising, for example, XGboost), Long short-term memory (LSTM), support vector machine (SVM) or random decision forests.
[0212] POM 154 - HYDROGEN PRODUCTION PLANT 12 MODELLING
[0213] Water electrolysis is an energy intensive process and a key process step in the production of Green Hydrogen. Each of the electrolyser modules 12a, 12b...12n of the Hydrogen production plant 12 is made up of hundreds of electrolytic cells working together to covert the renewable power into molecules of hydrogen governed by the time-dependent module efficiency q.
[0214] Each of the electrolyser modules 12[k]in the Hydrogen production plant 12 is modelled independently based on its historical performance data. The predicted operational characteristic variables utilized are:
[0215] Electrolyzer Power Consumed [EP(i,k)]
[0216] Electrolyzer Hydrogen Produced [EH(i,k)]
[0217] Which are based on number of predictor variables such as:
[0218] Demin Water Flow [ED(i,k)]
[0219] Average cell temperature [ECT(i,k)],
[0220] Average cell pressure [ECP(i,k)],
[0221] Current flowing through the electrodes [(i,k)]
[0222] Amongst other key process indicators.
[0223] Historical time series data for predictor and response variables are sampled over several months sampled at appropriate frequency [s] and are used to develop a model for the actual module efficiency. The model is built using equations derived from the predictor variables.
[0224] In addition, the totalizer variable is used to track the functioning age of the module, which is one of the predictor variables in the model. Reliability and maintenance event information from asset management system.
[0225] The model will be trained periodically or on demand (to create a relationship between response variables at time n with respect to predictor variables at each of the time instances starting from n-1 to n-k in intervals of fixed duration such as 15 minutes, or 1 hour.
[0226] In the training system various machine learning algorithms are used to create a mathematical relationship between the predicted and predictor variables.
[0227] POM 154 - AMMONIA LOOP MODELLING
[0228] The Ammonia Loop is a single unit equilibrium reactive system which processes the synthesis gas of nitrogen and hydrogen to produce ammonia. Nitrogen is provided by the ASU 16 which, in embodiments, is running continuously to provide Nitrogen.
[0229] Hydrogen is provided from the Hydrogen production plant 12 if it is running based on the availability of the renewable power at given instance or else hydrogen is fed from the Hydrogen storage 14.
[0230] Stoichiometric composition of synthesis gas is processed by the syn-gas compressor system and the product is refrigerated by another set of compressors and sent to storage.
[0231] The performance of the Ammonia loop is governed by the equilibrium conversion of the exothermic reaction and is monitored in real-time based on the predictive model for Ammonia flow to storage, AFI as a function various predictor variables, including:
[0232] Power consumed by Ammonia loop, APi ,
[0233] Ammonia loop pressure and Temperature, ALPi, ALTi
[0234] Feed flow rates of nitrogen and hydrogen streams, ANFi, AHFi
[0235] Ammonia plant syngas compressor pressure, ACPi.
[0236] Additional information on the health of the catalyst bed and timing of maintenance events may be used in the model to get the most realistic picture of the conversion loop efficiency.
[0237] A further aspect of the Ammonia loop is the different modes of operation. In embodiments, two main modes are present: Normal and Stand-by. The Normal model involves ramping up and down in response to the amount of Hydrogen available. This data is tracked in the DCS and is utilized to see any performance differences or to diagnose any process deviations from production planning. This time-dependent operational characteristic data may be utilized as inputs to the trained machine learning model to predict future operational behaviour.
[0238] As set out below, the model is trained periodically over a longer-range historical data set (which may be, for example, 6 months to a year) to capture all modes and different levels of ramp rates.
[0239] POM 154 - HYDROGEN STORAGE 14 MODELLING
[0240] The Hydrogen storage unit 14 comprises, in embodiments, Hydrogen purification trains, storage and a set of compressors which are operable in a dynamic fashion to direct the Hydrogen delivery to the Ammonia process plant and manage the Hydrogen inventory to avoid shutdowns due to lack of available gas resources.
[0241] The overall performance of the system is measured by achieving the specified set points on header pressure in a reliable and energy efficient manner. The compressors are modelled in terms of iso-entropic efficiencies based on operating temperatures and ambient conditions. Real-time condition monitoring of all the compressors is based on adaptive multi variate (Principal Component Analysis (PCA) and Partial Least Squares (PLS) models are built on moving 3-month window of historical data of key process tags.
[0242] Real-time tracking of Hydrogen storage may be based on first principal thermodynamic models based on using:
[0243] Storage system pressure and temperature, SPi, STi
[0244] Hydrogen compressor pressure and flow, HCPi, HCFi.
[0245] The efficiency of the compressor system is tracked using the compressor power consumed, CPi. In addition this system may perform the real-time monitoring of the Hydrogen purification system in terms of both efficiency and reliability.
[0246] POM 154 - ASU 16 MODELLING
[0247] In order to model the Air Separation Unit 16, in embodiments, multi-variate partial least squares (PLS) and principle component analysis (PCA) models along with engineering models are utilized. These models are operable to diagnose performance impacts and and identify preferred operating modes. Data from these models may be utilized as operational characteristic data input into a trained machine learning model.
[0248] Several key performance indicators (KPIs) may be selected. In non-limiting examples they may comprise specific power, N 2 recovery, and temperature differences in a heat exchanger forming part of the ASU. ) The KPIs are tracked in real-time for early detection and diagnosis of inefficient operations as well as emerging degradation of equipment health. The generation of the KPIs are not material to the present invention however these values may be utilised by the predictive machine learning model to build a predictive model of the performance of the ASU 16.
[0249] INDUSTRIAL GAS PLANT MODEL COMPONENT TRAINING AND PREDICTION
[0250] For each industrial gas plant, a machine learning model is assigned and implemented as set out above. For each plant, the machine learning model is operable to utilise a training process to generate equations which model the behaviour of the respective industrial gas plant. This is done using the predictor variables set out above for each industrial gas plant.
[0251] The training process may take historical time-dependent operational characteristic data as an input to train the machine learning model. The operational characteristic data may comprise physical measured data relating to the respective industrial gas plant such as, in non-limiting embodiments, input power, power usage, gas output, measured efficiency etc.
[0252] In addition, the operational characteristic data may comprise data generated by one or more physics-based models as discussed above. The physics-based models may take measured specific industrial gas plant characteristics (specific to each industrial gas plant) and may generate one or more metrics indicative of the performance of the industrial gas plant. These time-dependent metrics may then be used as inputted operational characteristic data to train the machine learning model assigned to the respective industrial gas plant.
[0253] Once a training process at a training time is complete, the model can be used to predict the behaviour of the respective industrial gas plant. In the prediction stage, the equations generated and stored in the training phase are used to enable predictions regarding future behaviour to be made.
[0254] In embodiments, an assessment of the accuracy of the machine learning model is made by comparing a value of the predicted future behaviour of each industrial gas plant for a pre-determined future time period with the actual behaviour of the industrial gas plant at the end of the predicted future time period. This enables determination of a prediction error value which provides a metric for the accuracy of the model.
[0255] If the model is insufficiently accurate, it may need to be trained at a further training time. The pre-determined training time may be selected based on the prediction error value which may, in embodiments, be when the prediction error value exceeds a pre-determined threshold.
[0256] In embodiments, the training time may be selected empirically on a periodic basis; for example, every 24 hours or every 48 hours as appropriate. Given, in embodiments, that historical data may extend over a number of months, training may not need to be so frequent. In embodiments, this periodic basis may be the default training time strategy.
[0257] However, in embodiments, this may be interrupted when the prediction error value exceeds the pre-determined threshold within the pre-determined empirical interval, in which case the training time is scheduled based on the prediction error value.
[0258] POM 154 SUMMARY
[0259] As discussed above, machine learning models are provided for each of the industrial gas plants forming the industrial gas complex. These machine learning models are trained on operational characteristic data generated, as described above, from measured historical time dependent data relating to the relevant plant and/or from time-dependent data generated from one or more physics-based models of the respective plant.
[0260] These models each generate predicted data relating to one or more of: the performance; the capability; the efficiency; the maintenance status; and/or the utilization of the relevant plant.
[0261] An example of a generated efficiency curve for a process variable is shown in Figure 7. Figure 7 shows a curve of efficiency of electrolyser vs load on an electrolyser. This curve is generated from time-dependent operational characteristic data from an electrolyser forming part of the Hydrogen plant 12 which is input into the respective machine learning model to generate operational characteristic data.
[0262] In addition to the predictions of the individual machine learning models assigned to each industrial gas plant, a further model may be utilized which determines the overall performance of the plant complex at a given instance is based on combining the efficiency of individual modules coming from each of the models above. Ensemble machine learning algorithms are employed to improve the quality of predictions and best models are selected to be used in the prediction system.
[0263] In other words, the time-varying operational characteristics for each of the industrial gas plants forming part of the plant complex for a pre-determined future period are predicted by each of the trained machine learning models and input into a further model to predict the production efficiency of the overall process plant complex. Data from each of the models may be input into the collective model on a periodic basis; for example, in non-limiting embodiments this may be every 15 minutes.
[0264] In terms of the Ammonia production plant in the exemplary embodiment, the efficiency determination enables a predicted determination of the Ammonia produced for a given level of energy input.
[0265] All the modelling carried out in the POM 154 is implemented as computer programs on one or more computers in the plant. Irrespective of the machine learning algorithm used, the model utilises a two step operation process where a training stage is required prior to a predictive stage. Both stages are implemented as computer programs on one or more computer systems.
[0266] Specialist and non-specialist hardware may also be used. For example, the training stage may involve use of Central Processing unit (CPU) and Graphical Processing Unit (GPU) components of a computer system. In addition, other specialist hardware may be used such as Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs) or other stream processor technologies.
[0267] The model execution computer(s) will be connected to other computer database systems where the data from the plant and weather data service will be stored. As the plant is operating, performance models are used to make predictions every 15 minutes to get the production profiles.
[0268] All the performance models along with some of the unit-operation level data is used in the RTOM 156 at a pre-defined frequency to optimize the operational efficiency and define the setpoints for different models.
[0269] METHOD OF OPERATION
[0270] Figure 6 shows a method according to an embodiment. Note the following steps need not be carried out in the order described below and some steps may be carried out concurrently with other steps.
[0271] In embodiments, a method of predicting operational characteristics of an industrial gas plant complex comprising a plurality of industrial gas plants is provided. The method is executed by at least one hardware processor.
[0272] At step 300, a machine learning model is assigned to each of the industrial gas plants forming the industrial gas plant complex. This model may take any suitable form as described above. It may utilize historical time-dependent operational characteristics of the industrial gas plant to generate equations to make future predictions.
[0273] At step 310, the respective machine learning model for each industrial gas plant is trained based on received historical time-dependent operational characteristic data for the respective industrial gas plant. This data may take any suitable form and may be specific to a particular type of industrial gas plant as described above. By historical is meant past operational characteristic data. This may be gathered in any suitable time window, and may include data within a moving window which extends up to but not including the present time. The window may in embodiments be six months to a year long.
[0274] The historical time-dependent operational characteristic data may comprise physical measured data relating to the respective industrial gas plant such as, in non-limiting embodiments, input power, power usage, gas output, measured efficiency etc.
[0275] In addition, the operational characteristic data may comprise data generated by one or more physics-based models as discussed above. The physics-based models may take measured specific industrial gas plant characteristics (specific to each industrial gas plant) and may generate one or more metrics indicative of the performance of the industrial gas plant. These time-dependent metrics may then be used as inputted operational characteristic data to train the machine learning model assigned to the respective industrial gas plant.
[0276] At step 320, the trained machine learning model for each industrial gas plant is executed to predict operational characteristics for each respective industrial gas plant for a pre-determined future time period. This prediction may optionally be used to control the behavior of the respective industrial gas plant, to predict likely usage, maintenance schedules, resource allocation or to identify process issues and potential problems.
[0277] For example, the predicted data may be used to infer other technical properties of the industrial gas plant(s). The predictions may be used to determine resource planning, maintenance schedules or servicing requirements. This scheduling of maintenance may be done in conjunction with determination of power resources and capacity of storage units. For example, the maintenance of a gas-generating component (e.g. electrolyzers, ASUs,
Ammonia production plant) may be scheduled to occur during a period when gas stores are high and predicted available renewable power is low so as to minimize disruption and maintain continuity of service provision.
[0278] In addition, the data may also be utilized to determine setpoint characteristics in step 330 below.
[0279] At step 330, the predicted operational characteristics determined by the models in step 320 for each respective industrial gas plant are utilized in a further collective model to generate an operational performance metric of the industrial gas plant complex. In the Ammonia production plant in the exemplary embodiment, the efficiency determination enables a predicted determination of the Ammonia produced for a given level of energy input.
[0280] At step 340, the predicted data for a pre-determined future time period is compared to actual measured data at the end of the time period. This comparison is used to infer other technical properties of the industrial gas plant(s). The predictions may be used to determine resource planning, maintenance schedules or servicing requirements.
[0281] In embodiments, a prediction for a pre-determined time period (e.g. a time window of, for example, 2 weeks, one month, six months from generation of the predicted data or from a time stamp in the predicted data) is then compared to actual data for the time window or time period at the end of the time period covered by the predicted data (e.g. after 2 weeks/one month/six months from the predicted data generation or from the time stamp in the predicted data). This enables potential problems in the plant complex 10 to be identified early since deviation of any industrial gas plant or storage system from a predicted model based on past actual behaviour may indicate development of a production or maintenance problem.
[0282] By using such a method, potential future problems can be identified early, enabling remedial action to be taken before any critical failures or unplanned shut-downs of the plant services are required for urgent maintenance or repair.
[0283] In addition, in embodiments, the scheduling of maintenance may be done in conjunction with determination of power resources and capacity of storage units. For example, the maintenance of a gas-generating component (e.g. electrolyzers, ASUs, Ammonia production plant) may be scheduled to occur during a period when gas stores are high and predicted available renewable power is low so as to minimize disruption and maintain continuity of service provision.
[0284] In embodiments, the predicted data may optionally be used to control the one or more industrial gas plants in response to the predicted operational characteristics of the industrial gas plants for the pre-determined future time period. For example, one or more operational setpoints of the one or more industrial gas plants may be set in dependence upon the predicted behavior.
[0285] The control in step 340 may be done in conjunction with the method described in steps 200 to 250 where predicted power availability is utilized in combination with the predicted efficiency determination in step 330 to enable set points to be determined based on both predicted power availability and also plant efficiency.
[0286] At step 350, a determination is made as to whether a further training process is required. This may be based on an empirical metric such as a pre-determined time period. Alternatively, it may be based on an assessment of the accuracy of the machine learning model by comparing a value of the predicted operational characteristics for a pre-determined future time period with the actual operational characteristics of the industrial gas plant at the end of the predicted future time period. This enables determination of a prediction error value which provides a metric for the accuracy of the model.
[0287] If it is determined that the model needs retraining, a training time may be scheduled and the method may move back to training in step 310. Note that this may occur following any of steps 320, 330 or 340.
[0288] REAL-TIME OPTIMIZATION MODULE (RTOM) 156
[0289] The RTOM 156 comprises a system to determine the rate at which various industrial gas plants should run to manage the renewable hydrogen production and storage optimally while maximizing ammonia production. In other words, the RTOM 156 enables real-time optimization of an industrial gas plant complex using renewable power. More particularly, in embodiments,
[0290] In embodiments, the system solves an optimization algorithm applied to a dynamic mathematical model of an industrial gas plant complex. The RTOM 156 system uses the predicted powers WPi and SPi and state of the industrial gas plants such as efficiencies inferred from plant-specific factors discussed above in relation to the POM 154 such as current, pressure, temperature and flowrate measurements. These values are taken as the inputs and applies an optimization algorithm to propose optimal rates at which to run the ammonia plant for time periods from c+1 to c+p.
[0291] The rates of the other industrial gas plants such as Hydrogen production plant 12, hydrogen compression and storage system 14, the air separation unit 16, Nitrogen storage 16a and the water plant are linked to ammonia rate and are controlled by lower-level controllers as described above. Only the first value from the list of optimal value for time c+1 is implemented, and the calculation is repeated at time c+1 with new data as it becomes available.
[0292] The RTOM 156 may also utilise data relating to the resource storage devices or energy storage devices of the storage resource 28. As noted above, the energy storage devices may comprise one or more of: a Battery Energy Storage System (BESS) 28a, a Compressed/Liquid Air Energy Systems (CAES or LAES) 28b or a Pumped Hydro Storage System (PHSS) 28c.The status, operational characteristics, availability, resource storage level and ease of power availability of each of the units of the storage resource 28 may be factored in to the optimization problem.
[0293] The RTOM 156 system is implemented on a computer and receives various inputs from other computer systems. The predicted power comes from PPM 152.The state of the industrial gas plants are represented by equations relating power consumptions of various units such as electrolyzer (ECi), hydrogen compressor (CPi), ammonia plant (APi), and ASU (NPi) to process variables related to these units.
[0294] The RTOM 156 system solves an optimization problem which seeks to maximize ammonia production given constraints on total amount of predicted power available over the next p time periods, amount of hydrogen available in storage, physics or data-based equations describing process plant operation.
[0295] Typically such problems are Mixed Integer Non Linear Programs (MINLP) because the process plant equations are non-linear and some of the decisions require some equipment to be run in one of a few possible modes leading to integer variables. The optimization generates set points from time c+1 to c+p to balance the predicted generated power and consumed power so that right amount of hydrogen is produced and ammonia plant runs at the correct rate to maximize ammonia production. The RTOM 156 system also accounts for hydrogen storage and hydrogen may either be stored or consumed from storage based on future power prediction.
[0296] In addition, the RTOM 156 system can choose to recommend that the plant may go into standby or shutdown modes based on power availability and equipment availability information. The output of the RTOM 156 system is a recommend ammonia production rate that is transferred automatically to advanced control systems controlling the ammonia plant, ASU, electrolyzer, water plant and hydrogen compression and storage.
[0297] An example of this is shown in Figure 8 which shows the optimal Ammonia plant rate as a function of time for a 48 hour predicted period.
[0298] METHOD OF OPERATION
[0299] In embodiments, there is provided a method of controlling an industrial gas plant complex comprising a plurality of industrial gas plants powered by one or more renewable power sources. The method is executed by at least one hardware processor.
[0300] At step 410, time-dependent predicted power data for a pre-determined future time period from the one or more renewable power sources is received. In non-limiting embodiments, this may be determined by the PPM 152 in accordance with the process and method discussed at steps 200 to 250. Alternatively, the predicted power data may be obtained in accordance with any other suitable process.
[0301] At step 420, time-dependent predicted operational characteristic data for each industrial gas plant is received. In this context "industrial gas plant" may also include industrial gas storage, for example, Hydrogen, Nitrogen and/or Ammonia storage as described above in the present embodiments.
[0302] The operational characteristic data may, in embodiments, be generated in accordance with the protocols described in relation to the POM 156 and method steps 300 to 350 of Figure 6. However, said data may also be determined in accordance with any other suitable process.
[0303] At step 430, the predicted power data and predicted characteristic data is utilized in an optimization model to generate a set of state variables (which may be optimized state variables) for the plurality of industrial gas plants. In embodiments, this may be done by solving an optimization problem. For example, in non-limiting embodiments the optimization model may define the predicted power data and predicted characteristic data as a set of non-linear equations. Storage resource data may optionally be included in the power data. The state variables are then generated by solving the set of non-linear equations.
[0304] At step 440, the generated state variables (which may be optimized state variables) are utilized to generate a set of control set points for the plurality of industrial gas plants. The set points may be defined to achieve any specified goal. For example, the set points may be defined at a particular time to ensure that the industrial gas plant(s) are operated efficiently and effectively given the power and storage resources available. The set points may alternatively or additionally be utilized to maximize the production of industrial gas given the predicted power availability.
[0305] As a further example, the predicted power availability and predicted efficiency and operational characteristics of the individual industrial gas plants and/or the industrial gas plant complex as a whole may be utilized to prevent power starvation of the individual plants and/or plant complex or to increase production in situations where power availability is plentiful at the present time but a future shortfall is predicted.
[0306] At step 450, the control set points are sent to a control system to control the industrial gas plant complex by adjusting one or more control set points of the industrial gas plants.
[0307] In summary, in exemplary embodiments a control and optimization system for a industrial gas plant complex is provided. The industrial gas plant complex comprises a plurality of industrial gas plants, including a Hydrogen production plant utilizing electrolysis of water, an air separation plant for production of nitrogen, an ammonia synthesis plant to produce ammonia, a hydrogen storage system and an ammonia storage and shipment system.
[0308] In exemplary embodiments, the system seeks to maximize ammonia production given an uncertain future power input for the system. The system also includes a machine learning based program to predict future power input based on weather forecast. This program continuously learns from environmental and weather patterns and power generated to make future power generation predictions. The system also includes another machine learning program to learn from industrial gas plants operating data and modify the mathematical model used for optimization.
[0309] While the invention has been described with reference to the preferred embodiments depicted in the figures, it will be appreciated that various modifications are possible within the spirit or scope of the invention as defined in the following claims.
[0310] In the specification and claims, the term "industrial gas plant" is intended to refer to process plants which produce, or are involved in the production of industrial gases, commercial gases, medical gases, inorganic gases, organic gases, fuel gases and green fuel gases either in gaseous, liquified or compressed form.
[0311] For example, the term "industrial gas plant" may include process plants for the manufacture of gases such as those described in NACE class 20.11 and which includes, non exhaustively: elemental gases; liquid or compressed air; refrigerant gases; mixed industrial gases; inert gases such as carbon dioxide; and isolating gases. Further, the term "industrial gas plant" may also include process plants for the manufacture of industrial gases in NACE class 20.15 such as Ammonia, process plants for the extraction and/or manufacture of methane, ethane, butane or propane (NACE classes 06.20 and 19.20), and manufacture of gaseous fuels as defined by NACE class 35.21. The above has been described with respect to the European NACE system but is intended to cover equivalent classes under the North American classifications SIC and NAICS. In addition, the above list is non-limiting and non exhaustive.
[0312] In some of the examples a hydrogen storage system and in some cases a purification unit are shown. However, it will be appreciated that the present invention can be implemented without the use of a hydrogen storage system or purification unit, which are only shown here for completeness.
[0313] In this specification, unless expressly otherwise indicated, the word "or" is used in the sense of an operator that returns a true value when either or both of the stated conditions are met, as opposed to the operator "exclusive or" which requires only that one of the conditions is met. The word "comprising" is used in the sense of "including" rather than to mean "consisting of'.
[0314] In the discussion of embodiments of the present invention, the pressures given are absolute pressures unless otherwise stated.
[0315] All prior teachings above are hereby incorporated herein by reference. No acknowledgement of any prior published document herein should be taken to be an admission or representation that the teaching thereof was common general knowledge in Australia or elsewhere at the date thereof.
[0316] Where applicable, various embodiments provided by the present disclosure may be implemented using hardware, software, or combinations of hardware and software. Also, where applicable, the various hardware components and/or software components set forth herein may be combined into composite components comprising software, hardware, and/or both without departing from the spirit of the present disclosure. Where applicable, the various hardware components and/or software components set forth herein may be separated into sub-components comprising software, hardware, or both without departing from the scope of the present disclosure. In addition, where applicable, it is contemplated that software components may be implemented as hardware components and vice-versa.
[0317] Software, in accordance with the present disclosure, such as program code and/or data, may be stored on one or more computer readable mediums. It is also contemplated that software identified herein may be implemented using one or more general purpose or specific purpose computers and/or computer systems, networked and/or otherwise. Where applicable, the ordering of various steps described herein may be changed, combined into composite steps, and/or separated into sub-steps to provide features described herein.
[0318] While various operations have been described herein in terms of "modules", "units" or "components," it is noted that that terms are not limited to single units or functions. Moreover, functionality attributed to some of the modules or components described herein may be combined and attributed to fewer modules or components. Further still, while the present invention has been described with reference to specific examples, those examples are intended to be illustrative only, and are not intended to limit the invention. It will be apparent to those of ordinary skill in the art that changes, additions or deletions may be made to the disclosed embodiments without departing from the spirit and scope of the invention. For example, one or more portions of methods described above may be performed in a different order (or concurrently) and still achieve desirable results.
Claims (20)
1. A method of controlling an industrial gas plant complex comprising a plurality of industrial gas plants powered by one or more renewable power sources, the method being executed by at least one hardware processor, the method comprising:
receiving time-dependent predicted power data for a pre-determined future time period from the one or more renewable power sources;
receiving time-dependent predicted operational characteristic data for each industrial gas plant;
utilizing the predicted power data and predicted characteristic data in an optimization model to generate a set of state variables for the plurality of industrial gas plants;
utilizing the generated state variables to generate a set of control set points for the plurality of industrial gas plants; and
sending the control set points to a control system to control the industrial gas plant complex by adjusting one or more control set points of the industrial gas plants.
2. The method of claim 1, wherein the optimization model defines the predicted power data and predicted characteristic data as a set of non-linear equations.
3. The method of claim 2, wherein the state variables are generated by solving the set of non-linear equations.
4. The method of claim 1, wherein the time-dependent predicted power data is generated from a trained machine learning model.
5. The method of claim 4, wherein the time-dependent predicted power data is obtained by:
obtaining historical time-dependent environmental data associated with the one or more renewable power sources;
obtaining historical time-dependent operational characteristic data associated with the one or more renewable power sources;
training a machine learning model based on the historical time-dependent environmental data and the historical time-dependent operational characteristic data; and executing the trained machine learning model to predict available power resources for the one or more industrial gas plants for a pre-determined future time period.
6. The method of claim 1, wherein the time-dependent predicted operational characteristic data is generated from a trained machine learning model for each of the industrial gas plants.
7. The method of claim 6, wherein the time-dependent predicted operational characteristic data for each industrial plant is obtained by:
assigning a machine learning model to each of the industrial gas plants forming the industrial gas plant complex;
training the respective machine learning model for each industrial gas plant based on received historical time-dependent operational characteristic data for the respective industrial gas plant; and
executing the trained machine learning model for each industrial gas plant to predict operational characteristics for each respective industrial gas plant for a pre-determined future time period.
8. The method of claim 1, wherein the industrial gas plant complex comprises storage resources comprising one or more industrial gas storage vessels and/or one or more energy storage resources.
9. The method of claim 8, wherein the one or more energy storage resources comprises one or more of: battery energy storage systems; compressed air energy storage; liquid air energy storage; or pumped hydroelectric energy storage.
10. The method of claim 8, wherein the predicted power data further comprises data representative of operational parameters of the storage resources.
11. The method of claim 10, wherein the data representative of operational parameters of the storage resources comprises one or more of: resource storage availability; fill level; and utilization.
12. A system for controlling an industrial gas plant complex comprising a plurality of industrial gas plants powered by one or more renewable power sources, the system comprising:
at least one hardware processor operable to perform: receiving time-dependent predicted power data for a pre-determined future time period from the one or more renewable power sources; receiving time-dependent predicted operational characteristic data for each industrial gas plant; utilizing the predicted power data and predicted characteristic data in an optimization model to generate a set of state variables for the plurality of industrial gas plants; utilizing the generated state variables to generate a set of control set points for the plurality of industrial gas plants; and sending the control set points to a control system to control the industrial gas plant complex by adjusting one or more control set points of the industrial gas plants.
13. The system of claim 12, wherein the optimization model defines the predicted power data and predicted characteristic data as a set of non-linear equations.
14. The system of claim 13, wherein the state variables are generated by solving the set of non-linear equations.
15. The system of claim 12, wherein the time-dependent predicted power data is generated from a trained machine learning model.
16. The system of claim 12, wherein the time-dependent predicted operational characteristic data is generated from a trained machine learning model for each of the industrial gas plants.
17. A computer readable storage medium storing a program of instructions executable by a machine to perform a of controlling an industrial gas plant complex comprising a plurality of industrial gas plants powered by one or more renewable power sources, the method being executed by at least one hardware processor, the method comprising:
receiving time-dependent predicted power data for a pre-determined future time period from the one or more renewable power sources;
receiving time-dependent predicted operational characteristic data for each industrial gas plant;
utilizing the predicted power data and predicted characteristic data in an optimization model to generate a set of state variables for the plurality of industrial gas plants; utilizing the generated state variables to generate a set of control set points for the plurality of industrial gas plants; and sending the control set points to a control system to control the industrial gas plant complex by adjusting one or more control set points of the industrial gas plants.
18. The computer readable storage medium of claim 17, wherein the optimization model defines the predicted power data and predicted characteristic data as a set of non-linear equations.
19. The computer readable storage medium of claim 18, wherein the state variables are generated by solving the set of non-linear equations.
20. The computer readable storage medium of claim 17, wherein the time-dependent predicted power data is generated from a trained machine learning model and/or the time dependent predicted operational characteristic data is generated from a trained machine learning model for each of the industrial gas plants.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US17/193,052 | 2021-03-05 | ||
| US17/193,052 US11625020B2 (en) | 2021-03-05 | 2021-03-05 | Method and apparatus for controlling an industrial gas plant complex |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| AU2022201358A1 true AU2022201358A1 (en) | 2022-09-22 |
| AU2022201358B2 AU2022201358B2 (en) | 2024-05-16 |
Family
ID=80820022
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| AU2022201358A Active AU2022201358B2 (en) | 2021-03-05 | 2022-02-28 | Method and apparatus for controlling an industrial gas plant complex |
Country Status (8)
| Country | Link |
|---|---|
| US (2) | US11625020B2 (en) |
| EP (1) | EP4053655A1 (en) |
| CN (1) | CN115034399A (en) |
| AU (1) | AU2022201358B2 (en) |
| BR (1) | BR102022003674A2 (en) |
| CA (1) | CA3150631A1 (en) |
| CL (1) | CL2022000526A1 (en) |
| MX (1) | MX2022002511A (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP4335947A1 (en) * | 2022-09-06 | 2024-03-13 | Covestro Deutschland AG | Method and system for operating an electrochemical reactor |
| FI20235293A1 (en) * | 2023-03-13 | 2024-09-14 | Neste Oyj | Method and an apparatus for controlling a production plant |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7510640B2 (en) * | 2004-02-18 | 2009-03-31 | General Motors Corporation | Method and apparatus for hydrogen generation |
| US7411308B2 (en) * | 2005-02-26 | 2008-08-12 | Parmley Daniel W | Renewable energy power systems |
| US20070079611A1 (en) * | 2005-10-11 | 2007-04-12 | Doland George J | Renewable Power Controller for Hydrogen Production |
| CA2741129C (en) * | 2008-10-30 | 2018-07-17 | Next Hydrogen Corporation | Power dispatch system for electrolytic production of hydrogen from wind power |
| US9231267B2 (en) | 2009-02-17 | 2016-01-05 | Mcalister Technologies, Llc | Systems and methods for sustainable economic development through integrated full spectrum production of renewable energy |
| CN102693451B (en) | 2012-06-14 | 2014-11-19 | 东北电力大学 | Method for predicting ammonia process flue gas desulphurization efficiency based on multiple parameters |
| AU2013207551B2 (en) | 2012-07-20 | 2015-12-17 | Tata Consultancy Services Limited | Method and system for adaptive forecast of wind resources |
| TW201520784A (en) | 2013-11-29 | 2015-06-01 | Inst Information Industry | Renewable energy power generation prediction system and method and power allocation system |
| DK3154904T3 (en) * | 2014-06-16 | 2018-12-03 | Siemens Ag | SYSTEM AND PROCEDURE FOR LOADING THE INTERMITTING RENEWABLE ENERGY FOR A POWER |
| CN209085657U (en) | 2017-08-02 | 2019-07-09 | 强力物联网投资组合2016有限公司 | For data gathering system related or industrial environment with chemical production technology |
| CA3133043C (en) | 2019-03-29 | 2023-08-15 | Asahi Kasei Kabushiki Kaisha | Apparatus, method, and program for generating an operation plan of a hydrogen production system |
-
2021
- 2021-03-05 US US17/193,052 patent/US11625020B2/en active Active
-
2022
- 2022-02-25 BR BR102022003674-8A patent/BR102022003674A2/en unknown
- 2022-02-28 EP EP22159309.8A patent/EP4053655A1/en active Pending
- 2022-02-28 AU AU2022201358A patent/AU2022201358B2/en active Active
- 2022-02-28 MX MX2022002511A patent/MX2022002511A/en unknown
- 2022-03-02 CA CA3150631A patent/CA3150631A1/en active Pending
- 2022-03-03 CL CL2022000526A patent/CL2022000526A1/en unknown
- 2022-03-04 CN CN202210214540.4A patent/CN115034399A/en active Pending
-
2023
- 2023-01-31 US US18/103,766 patent/US12105502B2/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| EP4053655A1 (en) | 2022-09-07 |
| AU2022201358B2 (en) | 2024-05-16 |
| CN115034399A (en) | 2022-09-09 |
| US12105502B2 (en) | 2024-10-01 |
| BR102022003674A2 (en) | 2023-05-09 |
| US20230185283A1 (en) | 2023-06-15 |
| US11625020B2 (en) | 2023-04-11 |
| MX2022002511A (en) | 2022-09-06 |
| CA3150631A1 (en) | 2022-09-05 |
| CL2022000526A1 (en) | 2022-11-18 |
| US20220283567A1 (en) | 2022-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11929613B2 (en) | Method and apparatus for managing predicted power resources for an industrial gas plant complex | |
| EP4053653A1 (en) | Method and apparatus for monitoring operational characteristics of an industrial gas plant complex | |
| US12105502B2 (en) | Method and apparatus for controlling an industrial gas plant complex | |
| AU2022205197B2 (en) | Method and apparatus for managing industrial gas production | |
| Samani et al. | An optimal operation strategy for collaborative flexibility provision of a carbon capture and utilization process with wind energy | |
| Nnabuife et al. | Integration of renewable energy sources in tandem with electrolysis: A technology review for green hydrogen production | |
| CN117613957A (en) | Optimal dynamic regulation control method and device for electro-hydrogen-ammonia | |
| US20240143854A1 (en) | Method and system for configuring an industrial gas plant complex powered by renewable power sources | |
| US20240211980A1 (en) | Method and apparatus for management of power in an industrial gas production facility | |
| EP4332694A1 (en) | A method and system for controlling production and storage of industrial gases | |
| BR102023026382A2 (en) | METHOD AND APPARATUS FOR POWER MANAGEMENT IN AN INDUSTRIAL GAS PRODUCTION PLANT | |
| Crevecoeur | An Optimal Operation Strategy for Collaborative Flexibility Provision of a Carbon Capture and Utilization Process with Wind Energy | |
| CN116341968A (en) | Method and system for analyzing flexibility and identifying bottleneck of renewable energy hydrogen production system under uncertainty condition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FGA | Letters patent sealed or granted (standard patent) |